SKILLEMALL.ai
RU Sign in

FB bbc-skill

Fetch Bilibili (哔哩哔哩) video comments for UP主 self-analysis. Use when the user asks to collect, download, export, or analyze comments on a Bilibili video (BV号 / URL / UID). Produces JSONL + summary.json suitable for further Claude Code analysis (sentiment, keywords, audience trends). Read-only; does not post/edit/delete.

Not recommendedcritical or high security findings · low grade F
ClawHub Hermes author: Agents365.ai v1.0.3 MIT-0 26 files body ≈ 1 503 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 69/100 · Nearly there — weak spots: result and completion, running it twice

AnalyzerMedia and videoAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
F
34/100
safety, quality, tests
Safety 60%
0
Quality 40%
85
Run on models
none yet
Process rating
B
69/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Tools and files w 18
60
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 12

  • high Exfiltration intent-browser-credential-store README_CN.md:126
    Accesses a browser credential / cookie store
    **推荐方式**：Chrome 插件 [**Get cookies.txt LOCALLY**](https://chromewebstore.google.com/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc)（开源、完全本地、不上传任何数据）。
  • high Exfiltration intent-browser-credential-store README.md:144
    Accesses a browser credential / cookie store
    [**Get cookies.txt LOCALLY**](https://chromewebstore.google.com/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc)
  • high Exfiltration intent-browser-credential-store README.md:147
    Accesses a browser credential / cookie store
    1. Install **Get cookies.txt LOCALLY** from the Chrome Web Store.
  • high Exfiltration intent-browser-credential-store references/cookie-extraction.md:18
    Accesses a browser credential / cookie store
    [**Get cookies.txt LOCALLY**](https://chromewebstore.google.com/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc)
  • high Exfiltration intent-browser-credential-store SKILL.md:48
    Accesses a browser credential / cookie store
    [**Get cookies.txt LOCALLY**](https://chromewebstore.google.com/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc)
Medium and low: 7
  • medium Exfiltration intent-browser-credential-store agents/openai.yaml:25
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    "Get cookies.txt LOCALLY" Chrome/Edge extension
    quoted
  • medium Exfiltration intent-browser-credential-store docs/index.html:255
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    <h3>Install the "Get cookies.txt LOCALLY" Chrome extension</h3>
    quoted
  • medium Exfiltration intent-browser-credential-store references/cookie-extraction.md:41
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    1. Firefox — `cookies.sqlite` via stdlib `sqlite3`, unencrypted
    quoted
  • medium Exfiltration intent-browser-credential-store references/cookie-extraction.md:51
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    1. Cookie DB: `~/Library/Application Support/Google/Chrome/<profile>/Cookies`
    quoted
  • medium Exfiltration intent-browser-credential-store references/cookie-extraction.md:65
    Accesses a browser credential / cookie store (detector / deny-list definition)
    On all OSes Firefox stores cookies in `cookies.sqlite` with values in
    detector
  • medium Exfiltration intent-browser-credential-store src/bbc/cookie/firefox.py:32
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    if (path / "cookies.sqlite").exists():
    quoted
  • medium Exfiltration intent-browser-credential-store src/bbc/cookie/firefox.py:39
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    db = profile / "cookies.sqlite"
    quoted

Files scanned: 26. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 321 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 69/100

  • 0Result and completion. Does not say what the result is
  • 30Running it twice. 2 mutating operations with no state check
  • 60Tools and files. Uses tools (web, git, python) that frontmatter does not declare
  • 60Consistency. The Hermes dialect needs category and tags
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 31 steps
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 3 branches, has a failure section
  • 100Execution cost. Instruction body is 1503 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +2Single-language instructions
  • +3Description length 321: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 31 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

External checks

ClawHub: suspicious
The skill does collect Bilibili comments as advertised, but it also silently self-updates and can automatically read browser session cookies, so it needs Review before installation.
LLM: suspicious (high) · VirusTotal: · 29 May 2026